browser_evaluate

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does disclose the default-disabled state and the need for manual confirmation—a key safety behavior. However, it does not describe what happens after execution (return value, errors, page state changes), leaving significant behavioral aspects unclear for a potentially destructive tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, dense, front-loaded sentence that conveys the core action and both critical constraints (default disabled, confirmation required). It is concise with zero wasted words and achieves maximum informational density.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is complex and high-risk (JavaScript execution), yet the description omits the return format, error behavior, and any explicit side-effect warnings. For an agent to safely and effectively use this tool, it needs more detail about what the tool returns or how it affects the page. The lack of output schema increases the burden, which this description does not meet.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It clarifies the 'expression' parameter's purpose and explains the 'confirmed' flag's role. However, 'task_id' is entirely unaddressed, and there is no detail on expression syntax, limits, or evaluation context. This partial coverage is insufficient with three parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states '执行JavaScript表达式' (execute JavaScript expression), which is a specific verb + resource. This uniquely distinguishes it from all sibling browser tools (navigate, click, type, read, etc.) that perform other actions. The purpose is unambiguous and directly names the action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for usage: it is for executing JavaScript and comes with a default-disabled state and a human-confirmation requirement. While it doesn't explicitly name alternatives or when not to use it, the context makes the primary use case obvious. The operational prerequisite (enable + confirm) is stated, which is valuable guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.